Estimating Aboveground Biomass Using Allometric Models And Adaptive Learning Rate Optimization Algorithms

Abstract

Forest aboveground biomass (AGB) is imperative in the study of climate change and the carbon cycle in the global terrestrial ecosystem. Developing a credible approach to estimate forest biomass and carbon stocks is essential. Four allometric models were used with two optimization algorithms; Modified Root Mean Square Propagation (Modified RMSProp) and Modified Adaptive Moment Estimation (Modified Adam) were also used to train each model. Convergence was achieved after 1000 iterations of Modified RMSProp and 200 iterations of Modified Adam for all the models. A learning rate of 0.01 and exponential decay rates of 0.9 and 0.999 for the first and second momentum. A loss function of 0.5 Mean Square Error (0.5 MSE) was used and Root Mean Square Error (RMSE) was used to judge the accuracy of the models. The study showed that the optimization algorithms were both able to accurately optimize three of the four allometric models. While Modified Adam was the more efficient optimizer, it had the highest RMSE value 2.3910 and Modified RMSProp had the least RMSE value 0.37381. However, there was no statistically significant difference between the accuracy of the models optimized by both algorithms.